US11162888B2 - Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation - Google Patents
Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation Download PDFInfo
- Publication number
- US11162888B2 US11162888B2 US16/741,139 US202016741139A US11162888B2 US 11162888 B2 US11162888 B2 US 11162888B2 US 202016741139 A US202016741139 A US 202016741139A US 11162888 B2 US11162888 B2 US 11162888B2
- Authority
- US
- United States
- Prior art keywords
- data
- asset
- cui
- mount
- computing device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N17/00—Investigating resistance of materials to the weather, to corrosion, or to light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N17/00—Investigating resistance of materials to the weather, to corrosion, or to light
- G01N17/006—Investigating resistance of materials to the weather, to corrosion, or to light of metals
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N17/00—Investigating resistance of materials to the weather, to corrosion, or to light
- G01N17/04—Corrosion probes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G06K9/6256—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0418—Architecture, e.g. interconnection topology using chaos or fractal principles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
Definitions
- the present invention relates to inspection technologies, and, more particularly, relates to a cloud-based system for the prediction and detection of corrosion under insulation (CUI).
- CCI corrosion under insulation
- Corrosion under insulation is a condition in which an insulated structure such as a metal pipe suffers corrosion on the metal surface beneath the insulation. As the corrosion cannot be easily observed due to the insulation covering, which typically surrounds the entire structure, CUI is challenging to detect.
- the typical causes of CUI are moisture buildup that infiltrates into the insulation material. Water can accumulate in the annular space between the insulation and the metal surface, causing surface corrosion. Sources of water that can induce corrosion include rain, water leaks, and condensation, cooling water tower drift, deluge systems and steam tracing leaks. While corrosion usually begins locally, it can progress at high rates if there are repetitive thermal cycles or contaminants in the water medium such as chloride or acid.
- Embodiments of the present invention provide a system for predicting and detecting of corrosion under insulation (CUI) in an infrastructure asset.
- the system includes at least one infrared camera positioned to capture thermal images of the asset, at least one smart mount mechanically supporting and electrically coupled to the at least one infrared camera, the at least one smart mount including a wireless communication module, memory storage adapted to store thermal image data received from the at least one camera, a battery module operative to recharge the at least one infrared camera, an ambient sensor module adapted to obtain ambient condition data; and a structural probe sensor adapted to obtain CUI-related data from the asset.
- a wireless communication module adapted to store thermal image data received from the at least one camera
- a battery module operative to recharge the at least one infrared camera
- an ambient sensor module adapted to obtain ambient condition data
- a structural probe sensor adapted to obtain CUI-related data from the asset.
- the system further includes at least one computing device having a wireless communication module that is communicatively coupled to the at least one smart mount, the computing device configured with instructions for executing a machine learning algorithm taking as inputs thermal image data, ambient condition data and CUI-related data from the probe sensor, and outputting a CUI prediction regarding the asset, and a cloud computing platform adapted to receive and store the thermal image data, ambient condition data and CUI-related data from the probe sensor, and the prediction output by the computing device, the cloud computing platform adapted to receive verification data for updating the machine learning algorithm stored on the computing device.
- the at least one smart mount includes a fixture for supporting the infrared camera, the mount being rotatable and extendable to enable the infrared camera to be translated and tilted.
- asset includes identification tags and at least one smart mount further includes a standard camera operative to scan the identification tags on the asset.
- the ambient sensor module is operative to detect temperature, humidity and air pressure.
- the structural probe sensor can include a magnetometry sensor.
- system further comprises a control station communicatively coupled to the at least one smart mount and adapted to transmit configuration and control commands to the at least one smart mount.
- the machine learning algorithm employed by the at least one computing device can include a deep recurrent neural network, and in some implementations, the deep recurrent neural network is a long short-term memory (LSTM) network.
- the machine learning algorithm employed by the at least one computing device can further include a convolutional neural network.
- the at least one computing device is configured to perform noise reduction on the data received from the at least one smart mount.
- the system can have multi-node capability in which each of the at least one mounts can communicate with each other via their respective communication modules.
- Embodiments of the present invention also provide a method of obtaining data from an infrastructure asset for enabling prediction and detection of corrosion-under-insulation (CUI).
- the method comprises capturing thermal image data of the asset over time, probing the asset using an additional sensing mode to obtain additional probe over time, measuring ambient conditions to obtain ambient condition data over time, combining the thermal image, additional probe and ambient condition data into a computer readable file, and transmitting the file to a computing device that uses an algorithm that uses the thermal image, additional probe and ambient condition data to predict whether the asset contains CUI.
- Certain embodiments of the method further comprise scanning the asset for identification tags to obtain tag photo data and including the tag photo data in the computer readable file.
- the additional sensing mode can include, for example, a magnetometry sensor.
- the ambient condition data can include temperature, humidity and air pressure measurements.
- Embodiments of the present invention also provide a method of predicting corrosion-under-insulation (CUI) in an infrastructure asset using a cloud computing platform.
- the method comprises receiving a stream of data including thermal images of the asset, additional sensor probe data of the asset, and ambient conditions at the asset, executing, in real time, one or more machine learning algorithms using the received stream of data and weights received as updated from the cloud computing platform to generate a prediction as to whether the asset contains CUI, and transmitting the received stream of data and prediction to the cloud computing platform.
- CUI corrosion-under-insulation
- Some embodiments of the method further comprise filtering the received data for noise.
- the method can also include generating synthetic thermal image data based on ambient conditions and parameters of the asset using a thermal dynamic model.
- the synthetic thermal image data can be combined with the stream of including thermal images of the asset, additional sensor probe data of the asset, and ambient conditions at the asset to create a data training set for training a machine learning model.
- the machine learning model including a deep recurrent neural network. Implementations of the
- the machine learning model can include a long short memory network (LSTM).
- the machine learning model can further include a convolutional neural network.
- FIG. 1 is a schematic illustration of a cloud-based learning system for predicting and detecting CUI according to an embodiment of the present invention.
- FIG. 2 is a schematic illustration of an embodiment of the cloud-based system in which four infrared cameras and corresponding smart mounts and computing devices are deployed to monitor a structure for CUI.
- FIG. 3 is a block diagram showing functional elements of a smart mount according to an exemplary embodiment of the present invention.
- FIG. 4 is a block flow diagram illustrating a method for generating synthetic thermal image data structures according to an exemplary embodiment of the present invention.
- FIG. 5A is a flow chart of a method for acquiring data for CUI predication performed using an investigative kit according to an embodiment of the present invention.
- FIG. 5B is a flow chart of a method of real time CUI prediction according to an embodiment of the present invention.
- Embodiments of the present invention provide a predictive approach for detecting corrosion under insulation (CUI) taking into account dependent and independent surrounding variables. Thermal images of investigated assets are captured over time.
- CCI corrosion under insulation
- thermal images are captured over time, changes in phenomena can be readily observed, including the impact of temporary issues such as wind.
- the thermal images show temperature gradients indicative of locations vulnerable to CUI.
- Additional evaluations are performed with an independent non-destructive testing (NDT) technique, such as, for example, electromagnetic detection using a magnetometry sensor, to determine correlative relationships.
- NDT non-destructive testing
- This “sensor fusion” increases the accuracy of CUI detection, shadow detection, or abnormal process activities, the effects of which can be minimized.
- Ambient condition data such as the time of day, weather, process conditions, etc. are included as parameter inputs to machine learning algorithms that are used to generate conclusions from the multiple sources of input.
- a noise filter can be employed as a preprocessing step.
- non-determinative or confounding variables can be excluded, allowing the learning algorithms to zero-in on anomalies that are contrary to ambient conditions, and thus are more likely indicative of CUI.
- anomalies are recorded; afterwards field engineers can perform a verification inspection upon the locations where such anomalies occur.
- the results of the field inspection i.e., a “CUI verified” or “CUI not verified” can be stored on cloud-based platforms and used to train supervised machine learning systems, enabling the systems to become more ‘intelligent’ over time as parameters (weights, factors) are refined over time by a continually more encompassing data set.
- FIG. 1 is a schematic illustration of a cloud-based learning system 100 for prediction and detection of CUI according an embodiment of the present invention.
- FIG. 1 shows an exemplary structure 105 to be tested, in this case a set of insulated pipes.
- the insulated pipes of this example can comprise a metallic pipe conduit surrounded by one or more layers of insulation. Corrosion, when it occurs, tends form in the annular region between the insulation and the metallic pipe where moisture can become trapped and accumulate.
- one or more infrared cameras 110 are situated proximally to the structure 105 to capture infrared radiation and record thermal images emitted from the structure.
- the thermal images captured from the structure 105 reveal internal thermal contrasts within the structure that are undetectable in the visible spectrum radiation and can be indicative of moisture accumulation and/or corrosion.
- the infrared camera 110 preferably captures thermal images received from regions of the structure continuously over a selected duration, and/or intermittently at different times or dates.
- the camera 110 is adapted to convert the thermal images into a standardized computer-readable file format (i.e., thermograph files, jpgs).
- the infrared camera 110 is positioned on a mount 112 , which as described in greater detail below, can be “smart” and have a variety of components and functions.
- the mount can be implemented as a tripod.
- the mount 112 can be extendable to reach high elevations on the structure (e.g., by telescoping) and can include a mechanical head fixture coupling to the camera that has several degrees of freedom to pan and tilt at various angles with respect to a fixed plane.
- Field technical personal can set the extension and orientation of the mount head to capture thermal images from different areas of the structure, as required.
- identification tags can be posted on assets, or portions thereof.
- the precise geographical location of each tag can be determined using GPS.
- the identification tags can be implemented using image-based tags such as QR codes that are readable from a distance.
- a standard camera can be included along with the infrared camera on the mount to scan tags on the assets.
- tags of known size
- distances from the camera to the tags can be determined. Tagging enables simultaneous scanning and localization of the facility assets without the need to create complex three-dimensional CAD models of the facility.
- the infrared camera 110 can be physically and communicatively coupled to the mount 112 (e.g., wirelessly by Bluetooth or Wi-Fi communication).
- the mount 112 also includes or is coupled to one or more additional detectors, such as electromagnetic sensors (not shown in FIG. 1 ), which can be used to probe the structure and obtain supplemental readings to complement the data obtained by thermal imaging. In this manner, data from two or more distinct and independent sensing modes can be combined, referred to as “sensor fusion”, that can make downstream prediction and detection much more robust by reduction of false positive classifications.
- the mount 112 also includes sensors for detecting ambient conditions including temperature, humidity, and air pressure. Received thermal images can be associated with the ambient conditions and the current time at which the ambient conditions are recorded. This data comprises parameters used by the machine learning algorithms that contribute to the interpretation and classification of the thermal images captured from the structure.
- the mount 112 is communicatively coupled to a computing device 115 , which can be a tablet, laptop or any other suitable computing device with sufficient processing and memory capability that can be conveniently taken onsite in the field for use by field technical professionals.
- the mount 112 is operative to transmit thermographic files received from the camera 110 to the computing device 115 .
- the computing device 115 preferably stores executable applications for preprocessing and predictive analysis. Preprocessing can include image filtering steps for reducing noise in the images that can arise from many causes.
- the computer device also executes one or more machine learning algorithms that take the received thermograph files (thermal images) as inputs and output a prediction as to the probability that the thermal images contain anomalies of interest in real time.
- a plurality of machine learning algorithms can be used for CUI detection.
- convolutional networks which are useful for classifying images in detail, are used in a first stage
- recurrent neural networks which are useful for tracking changes over time, are used in an additional stage.
- the computing device 115 provides the output of the machine learning algorithms in an application user interface that can be conveniently consulted by field technical personnel. Real time predicative analysis in the field allows field technical personal to support observations and focus rapidly on high-risk areas of the structure that are more likely subject to corrosion damage.
- the computing device 115 communicates wirelessly via a network switch 120 (via wireless communication network 122 ) with a cloud computing platform 125 .
- Wireless network 122 can be a wireless local area network (WLAN), wireless wide area networks (WWAN), cellular networks or a combination of such networks.
- the cloud computing platform 125 comprises computing resources, typically dynamically allocated, including one or more processors (e.g., one or more servers or server clusters), that can operate independently or collaboratively in a distributed computing configuration.
- the cloud computing platform 125 includes database storage capacity for storing computer-executable instructions for hosting applications and for archiving received data for long term storage. For example, computing device 115 in the field can upload all thermal image and other data received to the cloud computing platform 125 for secure storage and for further processing and analysis.
- the computing device 115 can format and send data records in, for example, MySQL or another database format.
- An example database record can include, among other fields, a tagged asset location, a series of thermal images taken over time at a particular asset location (or a link thereto), the data value for the camera's ID (cameraID) of the camera that captured the thermal images, the time/date at which each image was captured, ambient conditions at the time/date (e.g., temperature), sensor fusion data (e.g., electromagnetic sensor data).
- the cloud database can store include a detailed geographical mapping of the location and layout of the infrastructure assets (e.g., from LiDAR data) and applications executed on the cloud platform can perform detailed analyses that combine the sensor data and predictive analyses with the detailed mapping of the assets to make risk assessments covering entire structures or groups of structures. Reports of such assessments and results of other processing performed at the cloud computing platform 125 are accessible to a control station 130 communicatively coupled to the cloud computing platform.
- the smart mount 112 it is possible for the smart mount 112 to format and transmit the received data to the cloud computing platform directly before analysis of the data is performed on site.
- FIG. 2 depicts an exemplary implementation of a cloud-based learning system for CUI prediction and detection more generally shown in FIG. 1 .
- this system 150 includes four sets of cameras, mounts and computing devices (“investigative kits”) positioned at various positions in proximity to structure 105 for capturing thermal image and other data.
- investigative kits four sets of cameras, mounts and computing devices
- FIG. 2 depicts an exemplary implementation of a cloud-based learning system for CUI prediction and detection more generally shown in FIG. 1 .
- this system 150 includes four sets of cameras, mounts and computing devices (“investigative kits”) positioned at various positions in proximity to structure 105 for capturing thermal image and other data.
- four investigative kits are used in this embodiment, it is again noted that fewer or a greater number of kits can be employed depending, for example, on the size of the structure or installation investigated.
- the system 150 is configured using a first infrared camera 152 associated with a first mount 154 and first computing device 156 positioned at a first location; a second infrared camera 162 associated with a second mount 164 and second computing device 166 positioned at a second location; a third infrared camera 172 associated with a third mount 174 and third computing device 176 positioned at a third location; and a fourth infrared camera 182 associated with a fourth mount 184 and fourth computing device 186 positioned at a forth location proximal to the asset 105 .
- Two-way wireless communications can be supported by all the mounts and computing devices of the system, each of which can thus communicate with each other.
- thermal image data received by the computing devices 156 , 166 , 176 , 186 can be transmitted to the cloud computing platform 125 via network switch 120 , and to control station 130 .
- the smart mounts 154 , 164 , 174 , 184 can communicate directly with the control station when wireless connectivity is available.
- each smart mount or computing device in the system can act as a communication node in a multi-node system, so that if one or more of the mounts or computing devices loses connectivity with the control station, data can be forwarded to other nodes that maintain connectivity.
- the control station 130 is configured to provide configuration and control commands to the smart mounts 154 , 164 , 174 , 184 or computing devices 156 , 166 , 176 , 186 .
- FIG. 3 is a block diagram showing functional elements of a smart mount according to an exemplary embodiment of the present invention.
- the smart mount 112 includes a camera coupling or mount 202 by means of which the infrared camera 110 can be securely mechanical affixed and electrically connected to the mount 112 .
- the camera coupling 202 can include expandable and rotatable elements, such as telescoping shafts, and various joints with degrees of freedom for enabling the camera to be translated and tilted to a desired position and orientation.
- the smart mount can be supported on a counterweighted movable to provide a steering sub-system on the ground.
- the smart mount 112 also includes a communication module 204 which can include an antenna, a transceiver, and electronic components configured to support two-way wireless communication with other smart mounts, computing devices, and the control station 130 .
- the smart mount also includes a memory module 206 which can be implemented using SSD card memory. If the infrared cameras are mounted in locations where signal obstructions result in suboptimal data rates that are inferior to the actual thermal image streaming rate, the onboard memory module can be used to store the thermal image stream to provide latency while the wireless attempts to support the data download.
- the smart mount 112 further includes an ambient sensor module 210 that can include temperature, humidity and pressure sensors.
- An additional structural probe sensor module 212 includes detectors that can be used to probe the structure for CUI using modes distinct from thermal imaging, including, without limitation, magnetic (magnetometry) and ultrasonic detectors. Together with the thermal images from the infrared camera, the structural probe sensor module provides the sensor fusion that enhances CUI prediction and risk assessment.
- An electrical power module 220 includes a battery module 222 of sufficient size to provide electrical power for the smart mount components and to charge the infrared camera battery via a power supply circuit 224 for a suitable data gathering period before requiring recharging. A suitable duration for data gathering can be for example, about 45 minutes to about 90 minutes. Larger or smaller batteries can be employed for longer or shorter data gathering periods.
- the field computing devices receive (ingest) thermal image, probe sensor and ambient condition data from the infrared cameras and smart mounts.
- the initial data ingest can be affected by conditions at the site, including, shadows, reflections and spurious signals.
- noise filtering mechanism integrated within the software as a preprocessing step to filter out noise and amplify the signal-to-noise ratio.
- ingested data can be filtered by dimensionality reduction and autoencoding techniques.
- linear or non-linear smoothing filters can be applied instead of or in addition to dimensionality reduction techniques.
- the noise filtering step helps discriminate CUI signals from shadows, reflections as well as normal near infrared thermal signals. While such noise and other artifacts in the data can be eventually recognized and compensated for in the machine learning process using multi-context embedding in the neural network stage, it can be more time and resource efficient to preprocess the data by filtering in this manner.
- Another refinement which can be used to enhance robustness to noise is the introduction of synthetic training data to supplement data taken from the field.
- Mathematical models including finite element analyses are based on the thermal dynamics of insulated metal structures and on thermal images taken in the field as a basis for calibration and comparison.
- the synthetic data can be to simulate and augment the thermal image training dataset.
- the synthetic data can also make the learning system more robust to different environmental conditions such as weather conditions, temperature, exposure to sun light, and material temperature behind the insulation, for example.
- the synthetic data can be generated locally by the computing devices or the cloud computing platform. In either case the synthetic data can incorporated in the training and application database at the cloud computing platform.
- FIG. 4 is a block flow diagram illustrating a method for generating synthetic thermal image data structures according to the present invention for supplementing a training set for a predictive machine learning model.
- the inputs for generating synthetic thermal images include environmental variables 302 (e.g., temperature, humidity, air pressure, time of day), asset parameters 304 (e.g., dimensions, position, material, insulation), and a set of thermal images 306 of various assets captured in the field (“field thermographs”).
- the environmental variables 302 and asset parameters 304 are input to a thermal dynamics model 310 that uses known thermodynamic properties of materials based on environmental conditions to generate a synthetic temperature map 315 of insulated assets over time, based on a random probability distribution of temperature and humidity conditions.
- the synthetic temperature map 315 and the field thermographs are inputs to an imaging model 320 . While images can be created from the temperature map alone, the field thermographs can be used as a basis of calibration and comparison. As an example, if a temperature maps of assets exhibits a tendency toward greater temperature contrasts than shown in field thermographs of similar asset under similar conditions, the imaging model can make weighting adjustments to bring the temperature map closer to the field thermographs. After such adjustments are made, the imaging model generates a set of synthetic thermal images 325 that can be used to supplement the field thermographs during training.
- FIG. 5A is a flow chart of a method for acquiring data for CUI predication performed using an investigative kit according to an embodiment of the present invention.
- the method begins in step 400 .
- step 402 smart mounts and cameras (infrared, standard) are installed at suitable locations to monitor assets at a facility.
- any tags posted on the assets are scanned.
- step 406 thermal image, sensor fusion, and ambient condition data are captured and stored in memory.
- this information is transmitted to a local computing device for real time analysis.
- the method ends in step 410 .
- FIG. 5B is a flow chart of a method of real time CUI prediction according to an embodiment of the present invention.
- the method begins.
- the computing device receives the captured data from the smart mounts.
- the received data is filtered for noise.
- CUI prediction and detection is conducted using machine learning algorithms based on the filtered data and parameter weights from prior training.
- the machine learning algorithms can include deep learning techniques such as convolutional and recurrent neural networks.
- synthetic data is generated to supplement the data received from the smart mounts.
- prediction output is generated on a graphical user interface to be viewed by field technical personnel.
- the received data and the prediction output is transmitted to the cloud computing platform.
- the method ends.
Abstract
Description
Claims (12)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/741,139 US11162888B2 (en) | 2018-08-30 | 2020-01-13 | Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/117,937 US10533937B1 (en) | 2018-08-30 | 2018-08-30 | Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation |
US16/741,139 US11162888B2 (en) | 2018-08-30 | 2020-01-13 | Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/117,937 Continuation US10533937B1 (en) | 2018-08-30 | 2018-08-30 | Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation |
Publications (2)
Publication Number | Publication Date |
---|---|
US20200217777A1 US20200217777A1 (en) | 2020-07-09 |
US11162888B2 true US11162888B2 (en) | 2021-11-02 |
Family
ID=69141141
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/117,937 Active US10533937B1 (en) | 2018-08-30 | 2018-08-30 | Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation |
US16/741,139 Active US11162888B2 (en) | 2018-08-30 | 2020-01-13 | Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/117,937 Active US10533937B1 (en) | 2018-08-30 | 2018-08-30 | Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation |
Country Status (1)
Country | Link |
---|---|
US (2) | US10533937B1 (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200242900A1 (en) | 2019-01-24 | 2020-07-30 | Square Robot, Inc. | Systems, methods and apparatus for in-service tank inspections |
US11112349B2 (en) * | 2019-07-16 | 2021-09-07 | Saudi Arabian Oil Company | Metal loss determinations based on thermography machine learning approach for insulated structures |
CN113486868B (en) * | 2021-09-07 | 2022-02-11 | 中南大学 | Motor fault diagnosis method and system |
CN113837650B (en) * | 2021-10-12 | 2023-08-22 | 西南石油大学 | Cloud model-based corrosion risk early warning method for desulfurization device |
CN115828772B (en) * | 2023-02-14 | 2023-05-09 | 科大智能物联技术股份有限公司 | Rapid calculation method for billet temperature by combining forward mechanism and machine learning |
Citations (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040257464A1 (en) | 2003-06-20 | 2004-12-23 | Pandit Amol S. | Camera tripold with memory storage and power source |
US20050098728A1 (en) | 2003-09-25 | 2005-05-12 | Alfano Robert R. | Systems and methods for non-destructively detecting material abnormalities beneath a coated surface |
US20100033565A1 (en) | 2006-06-16 | 2010-02-11 | Worcester Polytechnic Institute | Infrared Defect Detection System and Method for the Evaluation of Powdermetallic Compacts |
US20100107767A1 (en) | 2008-11-06 | 2010-05-06 | Kane Russell D | Method and System for Detecting Corrosion Under Insulation |
US7902524B2 (en) | 2009-02-23 | 2011-03-08 | The Boeing Company | Portable corrosion detection apparatus |
US20130037420A1 (en) | 2011-08-10 | 2013-02-14 | Miki Funahashi | Method and apparatus for detecting moisture on metal and other surfaces, including surfaces under thermal insulation |
US20140208163A1 (en) | 2013-01-22 | 2014-07-24 | General Electric Company | Systems and methods for analyzing data in a non-destructive testing system |
CN204086134U (en) | 2014-07-31 | 2015-01-07 | 中国石油大学(北京) | A kind of corrosive pipeline detector |
US20150381948A1 (en) | 2014-04-10 | 2015-12-31 | Smartvue Corporation | Systems and Methods for Automated Cloud-Based Analytics for Security Surveillance Systems with Mobile Input Capture Devices |
US20160148363A1 (en) | 2013-03-14 | 2016-05-26 | Essess, Inc. | Methods and systems for structural analysis |
US20160284075A1 (en) | 2013-03-14 | 2016-09-29 | Essess, Inc. | Methods, apparatus, and systems for structural analysis using thermal imaging |
US20160343106A1 (en) | 2015-05-22 | 2016-11-24 | Board Of Trustees Of Michigan State University | Defect detection system using finite element optimization and mesh analysis |
US9518918B2 (en) | 2013-02-25 | 2016-12-13 | Subterrandt Limited | Detection system and method of detecting corrosion under an outer protective layer |
US20170176343A1 (en) * | 2015-12-17 | 2017-06-22 | Venkat R. Krishnan | Method and System For Inspecting A Pipe |
JP2018025497A (en) | 2016-08-10 | 2018-02-15 | 旭化成株式会社 | Maintenance assist device, maintenance assist program, and maintenance assist method |
US20180284735A1 (en) | 2016-05-09 | 2018-10-04 | StrongForce IoT Portfolio 2016, LLC | Methods and systems for industrial internet of things data collection in a network sensitive upstream oil and gas environment |
US20180329904A1 (en) * | 2017-05-10 | 2018-11-15 | General Electric Company | Intelligent and automated review of industrial asset integrity data |
US20180335404A1 (en) | 2017-05-19 | 2018-11-22 | Saudi Arabian Oil Company | Two-Stage Corrosion Under Insulation Detection Methodology and Modular Vehicle with Dual Locomotion Sensory Systems |
US20180341876A1 (en) * | 2017-05-25 | 2018-11-29 | Hitachi, Ltd. | Deep learning network architecture optimization for uncertainty estimation in regression |
US20190087990A1 (en) * | 2017-09-17 | 2019-03-21 | Ge Inspection Technologies, Lp | Industrial asset intelligence |
US20190293552A1 (en) | 2018-03-21 | 2019-09-26 | The Boeing Company | Surface inspection system, apparatus, and method |
US20190331301A1 (en) | 2016-12-30 | 2019-10-31 | Du Yuchuan | Method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing |
US20190339150A1 (en) | 2018-05-04 | 2019-11-07 | Hydromax USA, LLC | Multi-sensor pipe inspection system and method |
-
2018
- 2018-08-30 US US16/117,937 patent/US10533937B1/en active Active
-
2020
- 2020-01-13 US US16/741,139 patent/US11162888B2/en active Active
Patent Citations (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040257464A1 (en) | 2003-06-20 | 2004-12-23 | Pandit Amol S. | Camera tripold with memory storage and power source |
US20050098728A1 (en) | 2003-09-25 | 2005-05-12 | Alfano Robert R. | Systems and methods for non-destructively detecting material abnormalities beneath a coated surface |
US20100033565A1 (en) | 2006-06-16 | 2010-02-11 | Worcester Polytechnic Institute | Infrared Defect Detection System and Method for the Evaluation of Powdermetallic Compacts |
US8596861B2 (en) | 2008-11-06 | 2013-12-03 | Honeywell International Inc | Method and system for detecting corrosion under insulation |
US20100107767A1 (en) | 2008-11-06 | 2010-05-06 | Kane Russell D | Method and System for Detecting Corrosion Under Insulation |
US7902524B2 (en) | 2009-02-23 | 2011-03-08 | The Boeing Company | Portable corrosion detection apparatus |
US20130037420A1 (en) | 2011-08-10 | 2013-02-14 | Miki Funahashi | Method and apparatus for detecting moisture on metal and other surfaces, including surfaces under thermal insulation |
US20140208163A1 (en) | 2013-01-22 | 2014-07-24 | General Electric Company | Systems and methods for analyzing data in a non-destructive testing system |
US20170336323A1 (en) | 2013-02-25 | 2017-11-23 | Subterandt Limited | Detection system and method of detecting corrosion under an outer protective layer |
US9518918B2 (en) | 2013-02-25 | 2016-12-13 | Subterrandt Limited | Detection system and method of detecting corrosion under an outer protective layer |
US9874516B2 (en) | 2013-02-25 | 2018-01-23 | Subterandt Limited | Detection system and method of detecting corrosion under an outer protective layer |
US20160148363A1 (en) | 2013-03-14 | 2016-05-26 | Essess, Inc. | Methods and systems for structural analysis |
US20160284075A1 (en) | 2013-03-14 | 2016-09-29 | Essess, Inc. | Methods, apparatus, and systems for structural analysis using thermal imaging |
US20150381948A1 (en) | 2014-04-10 | 2015-12-31 | Smartvue Corporation | Systems and Methods for Automated Cloud-Based Analytics for Security Surveillance Systems with Mobile Input Capture Devices |
CN204086134U (en) | 2014-07-31 | 2015-01-07 | 中国石油大学(北京) | A kind of corrosive pipeline detector |
US20160343106A1 (en) | 2015-05-22 | 2016-11-24 | Board Of Trustees Of Michigan State University | Defect detection system using finite element optimization and mesh analysis |
US20170176343A1 (en) * | 2015-12-17 | 2017-06-22 | Venkat R. Krishnan | Method and System For Inspecting A Pipe |
US20180284735A1 (en) | 2016-05-09 | 2018-10-04 | StrongForce IoT Portfolio 2016, LLC | Methods and systems for industrial internet of things data collection in a network sensitive upstream oil and gas environment |
JP2018025497A (en) | 2016-08-10 | 2018-02-15 | 旭化成株式会社 | Maintenance assist device, maintenance assist program, and maintenance assist method |
US20190331301A1 (en) | 2016-12-30 | 2019-10-31 | Du Yuchuan | Method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing |
US20180329904A1 (en) * | 2017-05-10 | 2018-11-15 | General Electric Company | Intelligent and automated review of industrial asset integrity data |
US20180335404A1 (en) | 2017-05-19 | 2018-11-22 | Saudi Arabian Oil Company | Two-Stage Corrosion Under Insulation Detection Methodology and Modular Vehicle with Dual Locomotion Sensory Systems |
US20180341876A1 (en) * | 2017-05-25 | 2018-11-29 | Hitachi, Ltd. | Deep learning network architecture optimization for uncertainty estimation in regression |
US20190087990A1 (en) * | 2017-09-17 | 2019-03-21 | Ge Inspection Technologies, Lp | Industrial asset intelligence |
US20190293552A1 (en) | 2018-03-21 | 2019-09-26 | The Boeing Company | Surface inspection system, apparatus, and method |
US20190339150A1 (en) | 2018-05-04 | 2019-11-07 | Hydromax USA, LLC | Multi-sensor pipe inspection system and method |
Non-Patent Citations (10)
Title |
---|
"Corrosion Under Insulation and Fireproofing". American Petroleum Institute, API Recommended Practice 583, Second Edition, 2019. |
Agarwala, Vinod S., Perry L. Reed, and Siraj Ahmad. "Corrosion detection and monitoring—A review." Corrosion 2000. NACE International, 2000. |
Bello, Opeyemi, et al. "Application of artificial intelligence techniques in drilling system design and operations: a state of the art review and future research pathways." SPE Nigeria Annual International Conference and Exhibition. Society of Petroleum Engineers, 2016. |
Burhani, Nurul Rawaida Ain, Masdi Muhammad, and Mokhtar Che Ismail. "Corrosion under insulation rate prediction model for piping by two stages of artificial neural network." AIP Conference Proceedings. vol. 2035. No. 1 AIP Publishing LLC, 2018. 6 pages. |
International Preliminary Report on Patentability in Corresponding PCT Application No. PCT/US2019/049154 dated Feb. 10, 2021. 15 pages. |
International Search Report and Written Opinion in Corresponding Patent Application No. PCT/US2019/049154 dated May 29, 2020. 21 pages. |
Malhotra P. et al, "Long Short Term Memory Networks for Anomaly Detection in Time Series," ESANN 2015 pp. 89-94. |
Prabhu, D. R., and W. P. Winfree. "Neural network based processing of thermal NDE data for corrosion detection." Review of progress in quantitative nondestructive evaluation. Springer, Boston, MA, 1993. 775-782. |
Written Opinion of the International Preliminary Examining Authority in Corresponding PCT Application No. PCT/US2019/049154 dated Dec. 15, 2020. 7 pages. |
Written Opinion of the International Preliminary Examining Authority in Corresponding PCT Application No. PCT/US2019/049154 dated Sep. 17, 2020. 7 pages. |
Also Published As
Publication number | Publication date |
---|---|
US10533937B1 (en) | 2020-01-14 |
US20200217777A1 (en) | 2020-07-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10643324B2 (en) | Machine learning system and data fusion for optimization of deployment conditions for detection of corrosion under insulation | |
US11162888B2 (en) | Cloud-based machine learning system and data fusion for the prediction and detection of corrosion under insulation | |
US20200072744A1 (en) | Inspection and failure detection of corrosion under fireproofing insulation using a hybrid sensory system | |
US10914653B2 (en) | Infrared imaging systems and methods for oil leak detection | |
GB2559291B (en) | UAVs for detecting defects in solar panel arrays | |
US8374821B2 (en) | Thermal powerline rating and clearance analysis using thermal imaging technology | |
WO2020123505A1 (en) | Inspection and failure detection of corrosion under fireproofing insulation using a hybrid sensory system | |
GB2459918A (en) | Thermal imaging | |
KR102217549B1 (en) | Method and system for soar photovoltaic power station monitoring | |
KR100944791B1 (en) | System for measurement of the water level and method for measurement of the water level | |
KR102136106B1 (en) | Photovoltaic power generation forecasting device | |
CN107687994A (en) | air detection system and method | |
US11892563B1 (en) | Detecting human presence in an outdoor monitored site | |
JP2020016527A (en) | Method of investigating stationary gas detection device installation site | |
Baeck et al. | Drone based near real-time human detection with geographic localization | |
US20240053287A1 (en) | Probability of detection of lifecycle phases of corrosion under insulation using artificial intelligence and temporal thermography | |
Kruijff et al. | On-site monitoring of environmental processes using mobile augmented reality (HYDROSYS) | |
Oufadel et al. | In-situ heat losses measurements of parabolic trough receiver tubes based on infrared camera and artificial intelligence | |
CN110427911A (en) | A kind of Approach for road detection, device, equipment and storage medium | |
CN109489824A (en) | A kind of intelligent infra-red thermal imaging system based on wireless transmission | |
WO2024035640A2 (en) | Probability of detection of lifecycle phases of corrosion under insulation using artificial intelligence and temporal thermography | |
JP2012124655A (en) | Disaster detection image processing system | |
EP4092315A1 (en) | System and method for inspecting stability of heat transfer pipe by using drone | |
Hatipoglu et al. | Overhead object projector: OverProjNet | |
Nooralishahi et al. | The registration of multi-modal point clouds for industrial inspection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
AS | Assignment |
Owner name: SAUDI ARAMCO TECHNOLOGIES COMPANY, SAUDI ARABIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:AL SHEHRI, ALI;AMER, AYMAN;ALDABBAGH, AHMAD;AND OTHERS;SIGNING DATES FROM 20180809 TO 20181202;REEL/FRAME:051512/0607 Owner name: SAUDI ARABIAN OIL COMPANY, SAUDI ARABIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SAUDI ARAMCO TECHNOLOGIES COMPANY;REEL/FRAME:051593/0569 Effective date: 20190508 Owner name: AVITAS SYSTEMS, INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LIM, SER NAM;UZUNBAS, MUSTAFA;SIGNING DATES FROM 20190701 TO 20190724;REEL/FRAME:051512/0697 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |